A Data-Driven PCA–OCSVM Framework for Intelligent Monitoring and Anomaly Detection of Grid-Connected PV Inverters Under Multitask Operation
Source abstract
Abstract
This study proposes an unsupervised anomaly detection method to identify the performance degradation in grid-connected photovoltaic (PV) inverters under multitask operation. Principal Component Analysis (PCA) and One-Class Support Vector Machine (OCSVM) were integrated to build a detection model using routine operational data. The key features include DC input, AC output, AC/DC ratio, and AC power variation, which are reduced to two principal components for anomaly boundary construction. The inverters were flagged as degraded if the AC/DC ratio was <0.96, the power fluctuation exceeded 20%, or the data fell outside the OCSVM-defined boundary. Compared with the Isolation Forest, the proposed method showed higher sensitivity. When applied to a 120 MW PV plant in Taiwan with 1292 inverters, including 55 PV-STATCOM units at night, the framework detected degradation in 5.4% of them. These results support their use in intelligent monitoring and predictive maintenance. In addition, through early fault detection and maintenance prioritization, the proposed framework contributes to enhancing reliability, reducing maintenance costs, and promoting the sustainable operation of utility-scale photovoltaic power plants.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Photovoltaic System Optimization Techniques · Islanding Detection in Power Systems · Power System Reliability and Maintenance
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Electrical Engineering, National Taiwan University of Science and Technology, Taipei City 10607, Taiwan
Department of Electrical Engineering, National Chin-Yi University of Technology, Taichung City 41170, Taiwan
References (20)
Show source-provided references
1. Reliability-Oriented Design and Analysis of PV Inverters Considering Mission Profiles
2. The Impact of PV Panel Positioning and Degradation on the PV Inverter Lifetime and Reliability10.1109/JESTPE.2020.3006267 ↗
3. Lifetime Evaluation of Grid-Connected PV Inverters Considering Panel Degradation Rates and Installation Sites10.1109/TPEL.2017.2678169 ↗
4. Maintenance Activity, Reliability, Availability, and Related Energy Losses in Ten Operating Photovoltaic Systems up to 1.8 MW10.1109/TIA.2020.3031547 ↗
5. Wang, W. (2021, January 22–24). A Non-Invasive Online Condition Monitoring Method for Both SiC MOSFET and DC-Link Capacitor in a Single-Phase Inverter. Proceedings of the 2021 Global Reliability and Prognostics and Health Management (PHM-Nanjing), Nanjing, China.10.1109/PHM-Nanjing52125.2021.9612967 ↗
6. (2018). IEEE Standard for Interconnection and Interoperability of Distributed Energy Resources with Associated Electric Power Systems Interfaces (Standard No. IEEE Std 1547-2018).
7. Flicker, J., Johnson, J., Reno, M.J., Azzolini, J.A., Hacke, P., and Thiagarajan, R. (2022, January 5–10). Inverter Reliability Estimation for Advanced Inverter Functionality. Proceedings of the 2022 IEEE 49th Photovoltaic Specialists Conference (PVSC), Philadelphia, PA, USA.10.2172/2003500 ↗
8. Five Years of Operating Experience at a Large, Utility-Scale Photovoltaic Generating Plant10.1002/pip.800 ↗
9. Vinson, W., Iradukunda, A., Huitink, D., Lee, J.-P., Kwon, M., and Oh, C.-Y. (2021, January 1–4). Combined Electromigration and Strain Accelerated Failure Test Development for Al Wire Bonds and Reliability Analysis of Grid-Tied Solar Inverter. Proceedings of the 2021 20th IEEE Intersociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems (iTherm), San Diego, CA, USA.10.1109/ITherm51669.2021.9503165 ↗
10. Monte Carlo Simulation with Incremental Damage for Reliability Assessment of Power Electronics10.1109/TPEL.2020.3044438 ↗
11. Liu, Y.-M., Kuo, C.-C., and Chen, H.-C. (2025). Nighttime Reactive Power Optimization for Large-Scale PV Plants: Minimizing Compensation Equipment Investment. Appl. Sci., 15.10.20944/preprints202509.0702.v1 ↗
12. Liu, Y.-M., Kuo, C.-C., and Chen, H.-C. (2025). A Hybrid GA–Digital Twin Strategy for Real-Time Nighttime Reactive Power Compensation in Utility-Scale PV Plants. Appl. Sci., 15.10.20944/preprints202509.1108.v1 ↗
13. Montgomery, D.C., and Runger, G.C. (2018). Applied Statistics and Probability for Engineers, Wiley. [7th ed.].
14. Jolliffe, I.T. (2002). Principal Component Analysis, Springer. [2nd ed.].
15. Principal Component Analysis10.1002/wics.101 ↗
16. Photovoltaic Inverter Failure Mechanism Estimation Using Unsupervised Machine Learning and Reliability Assessment10.1109/TR.2024.3359540 ↗
17. Fragoso, V., Scheirer, W., Hespanha, J., and Turk, M. (2016, January 4–8). One-Class Slab Support Vector Machine. Proceedings of the 23rd International Conference on Pattern Recognition (ICPR), Cancun, Mexico.10.1109/ICPR.2016.7899670 ↗
18. One-Class SVM Probabilistic Outputs10.1109/TNNLS.2024.3395148 ↗
19. Orosz, T., Rassõlkin, A., Arsénio, P., Poór, P., Valme, D., and Sleisz, Á. (2024). Current Challenges in Operation, Performance, and Maintenance of Photovoltaic Panels. Energies, 17.10.3390/en17061306 ↗
20. Walker, A., Lockhart, E., Desai, J., Ardani, K., Klise, G., Lavrova, O., Tansy, T., Deot, J., Fox, B., and Pochiraju, A. (2025, October 28). Model of Operation and Maintenance Costs for Photovoltaic Systems, Available online: https://www.nrel.gov/docs/fy20osti/74840.pdf.